{"id":"https://openalex.org/W92939709","doi":"https://doi.org/10.21437/interspeech.2004-318","title":"Harmonicity based monaural speech dereverberation with time warping and F0 adaptive window","display_name":"Harmonicity based monaural speech dereverberation with time warping and F0 adaptive window","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W92939709","doi":"https://doi.org/10.21437/interspeech.2004-318","mag":"92939709"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-318","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111931228","display_name":"Masato Miyoshi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masato Miyoshi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5049272790","display_name":"Parham Zolfaghari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Parham S. Zolfaghari","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021240106"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1217,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76280876,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"873","last_page":"876"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.7289553880691528},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7226011753082275},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.678748369216919},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6309902667999268},{"id":"https://openalex.org/keywords/inverse-filter","display_name":"Inverse filter","score":0.5753999948501587},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.4871928095817566},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.47734859585762024},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.46920245885849},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.438754677772522},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3697185516357422},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.22889158129692078},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.188189297914505},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18093067407608032},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08517026901245117},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07757395505905151}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.7289553880691528},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7226011753082275},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.678748369216919},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6309902667999268},{"id":"https://openalex.org/C2779948431","wikidata":"https://www.wikidata.org/wiki/Q17092649","display_name":"Inverse filter","level":3,"score":0.5753999948501587},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.4871928095817566},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.47734859585762024},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.46920245885849},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.438754677772522},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3697185516357422},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.22889158129692078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.188189297914505},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18093067407608032},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08517026901245117},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07757395505905151},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-318","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1867584760","https://openalex.org/W2006239277","https://openalex.org/W2050693797","https://openalex.org/W2086286498","https://openalex.org/W2126681966","https://openalex.org/W2140365942","https://openalex.org/W2149014962","https://openalex.org/W2183997954"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W1670332068","https://openalex.org/W4321794819","https://openalex.org/W2072124114","https://openalex.org/W2944394647"],"abstract_inverted_index":{"Although":[0],"a":[1,12,17,28,42,76,85],"number":[2],"of":[3,41,50,75,93,146],"dereverberation":[4,9,31,66,144],"methods":[5],"have":[6],"been":[7],"reported,":[8],"is":[10,20,79],"still":[11],"challenging":[13],"problem":[14],"especially":[15],"when":[16,89,125],"single":[18],"microphone":[19],"used.":[21],"To":[22],"overcome":[23],"this":[24,97,112],"problem,":[25],"we":[26,99],"proposed":[27],"harmonicity":[29,49],"based":[30,46],"method":[32],"(HERB).":[33],"HERB":[34,58,101],"can":[35,140],"blindly":[36],"estimate":[37,120],"the":[38,48,55,65,70,91,143],"inverse":[39],"filter":[40],"room":[43],"transfer":[44],"function":[45],"on":[47],"speech":[51,77],"signals":[52],"and":[53,106],"dereverberate":[54],"signals.":[56],"However,":[57],"uses":[59],"an":[60,107,137],"imprecise":[61],"assumption":[62],"that":[63,68,132],"hinders":[64],"performance,":[67],"is,":[69],"fundamental":[71],"frequency":[72],"(":[73],")":[74],"signal":[78],"assumed":[80],"to":[81,110,119],"be":[82],"constant":[83],"within":[84],"short":[86],"time":[87,103,133],"frame":[88],"extracting":[90],"features":[92],"harmonic":[94,121],"components.":[95],"In":[96],"paper,":[98],"combine":[100],"with":[102,136],"warping":[104,134],"analysis":[105,135],"adaptive":[108,138],"window":[109,139],"remove":[111],"bottleneck.":[113],"This":[114],"extension":[115],"makes":[116],"it":[117],"possible":[118],"components":[122],"precisely":[123],"even":[124],"their":[126],"frequencies":[127],"change":[128],"rapidly.":[129],"Experiments":[130],"show":[131],"effectively":[141],"improve":[142],"effect":[145],"HERB.":[147]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
